Benchmark menu

Per-game leaderboard

GB2-05: Hex

This page shows the per-game leaderboard for GB2-05: Hex in the balanced filter. Entrants are ranked by their relative per-game score within this game.

GB2-05: Hex

Hex

Hex is a connection game on a hexagonal grid where players race to join opposite board edges, with a swap option after the first move.

Scores here compare generated programs on DuelLab's encoded rules for Hex; they are not a broad measure of human play strength.

Entrants

Every admitted unique code identity for GB2-05: Hex. Elo and W/L/D use the public historical sequential-Elo result universe. Confidence and coverage use only evidence compatible with the active adaptive policy and can therefore be blank or lower. Capped draws are rated; unilateral model faults are listed separately.

Showing 49 entrants.
EntrantModelStatusScoreEloConfidenceW / L / DRated / attemptedOpponentsCapped drawsFaults / pluginsGeneration
E-ad7cf41c05ec3f64Claude Fable 5Under-covered56.215054 / 4 / 08 / 8400 / 1First pass · 2026-07-02
E-a75e9d71efa4a6bcClaude Opus 4.5Under-covered1.114690 / 2 / 02 / 2100 / 1First pass · —
E-924d7e6ee41b562eClaude Opus 4.8Under-covered40.114663 / 5 / 08 / 8400 / 1First pass · 2026-07-02
E-32c377b229530444Claude Opus 5Under-covered96.815908 / 2 / 010 / 10500 / 1First pass · 2026-07-25
E-d7111b534ebcaba2Claude Opus 5Under-covered100.015989 / 1 / 010 / 10500 / 1First pass · 2026-07-25
E-e0a09b1ea3f11175Claude Sonnet 5Under-covered33.114952 / 2 / 04 / 4200 / 1First pass · 2026-07-02
E-a0518a43c688d1e2North Mini CodeUnder-covered0.014670 / 2 / 02 / 2100 / 1First pass · 2026-07-02
E-7603462aff103041Gemini 3.1 Flash LiteUnder-covered44.814953 / 3 / 06 / 6300 / 1Repaired · 2026-07-02
E-a7ce764239377b3fGemini 3.5 FlashUnder-covered53.714994 / 4 / 08 / 8400 / 1Repaired · 2026-07-02
E-c311887ca24f8a76Gemini 3.5 Flash LiteUnder-covered30.414432 / 6 / 08 / 8400 / 1Repaired · 2026-07-24
E-e3c1bc55ae62b8dbGemini 3.5 Flash LiteUnder-covered25.714192 / 8 / 010 / 10500 / 1Repaired · 2026-07-24
E-9e479871cca0aeaaGemini 3.6 FlashUnder-covered82.115866 / 0 / 06 / 6300 / 1Repaired · 2026-07-24
E-c7d3f2597dfefeb3Gemini 3.6 FlashUnder-covered71.815306 / 4 / 010 / 10500 / 1Repaired · 2026-07-24
E-fd1bc1e2e6ac48fbGemma 4 31BUnder-covered47.415293 / 1 / 04 / 4200 / 1Repaired · 2026-07-02
E-9e5b308c41a36374GPT 5Under-covered58.615294 / 2 / 06 / 6300 / 1First pass · 2026-07-02
E-cafab3c275850d3bGPT-5.4Under-covered36.515032 / 2 / 04 / 4200 / 1First pass · 2026-07-02
E-0791f6b66243ec1aGPT-5.4 MiniUnder-covered33.414962 / 2 / 04 / 4200 / 1First pass · 2026-07-02
E-539afc540807da47GPT-5.4 MiniUnder-covered34.014692 / 4 / 06 / 6300 / 1First pass · 2026-07-02
E-ce84b7a3c6105fb2GPT-5.4 MiniUnder-covered34.114692 / 4 / 06 / 6300 / 1First pass · 2026-07-01
E-83cfa14483bf0d43GPT-5.4 NanoUnder-covered11.114420 / 4 / 04 / 4200 / 1First pass · 2026-07-02
E-8e40431df091d53fGPT-5.4 NanoUnder-covered80.415816 / 0 / 06 / 6300 / 1First pass · 2026-07-02
E-a0d8c8fd6b01598cGPT-5.4 NanoUnder-covered1.414700 / 2 / 02 / 2100 / 1First pass · 2026-07-09
E-ff2b4db95370e3d6GPT-5.4 NanoUnder-covered21.214381 / 5 / 06 / 6300 / 1First pass · 2026-07-01
E-ffa82d1e96e897abGPT-5.5Under-covered75.015506 / 2 / 08 / 8400 / 1First pass · 2026-07-02
E-e917387a1c57aa23GPT-5.6 LunaUnder-covered48.315313 / 1 / 04 / 4200 / 1First pass · 2026-07-10
E-d61f8454991c5422GPT-5.6 SolUnder-covered13.214470 / 4 / 04 / 4200 / 1First pass · 2026-07-10
E-9664e98d37ece097GPT-5.6 TerraUnder-covered57.015074 / 4 / 08 / 8400 / 1First pass · 2026-07-10
E-52b991e608dc1672LongCat 2.0Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-9061c6162106c911LongCat 2.0Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-fb8ac45946e32e22Minimax M3Under-covered1.114690 / 2 / 02 / 2100 / 1Repaired · 2026-07-02
E-952fba19b28982d5Kimi K2.7 CodeUnder-covered59.415584 / 0 / 04 / 4200 / 1Repaired · 2026-07-02
E-4a1443311507f194Kimi K3Under-covered26.415312 / 0 / 02 / 2100 / 1Repaired · 2026-07-21
E-5f76f577111bee8dNex N2 ProUnder-covered2.214720 / 2 / 02 / 2100 / 1Repaired · 2026-07-02
E-343b92f3dda3dcb5O3Under-covered24.314731 / 3 / 04 / 4200 / 1First pass · 2026-07-02
E-5ef540286ecbb63dGPT-OSS 120BUnder-covered33.314672 / 4 / 06 / 6300 / 1Repaired · 2026-07-02
E-53ce0020411c86d4Laguna S 2.1Pending0 / 0 / 00 / 0000 / 1First pass · 2026-07-24
E-62e15a037ee860c1Laguna S 2.1Pending0 / 0 / 00 / 0000 / 1Repaired · 2026-07-24
E-435ec29661cdc285Qwen3.7 MaxUnder-covered23.214711 / 3 / 04 / 4200 / 1Repaired · 2026-07-02
E-6cc7454f585005c4Qwen3.7 PlusUnder-covered36.415032 / 2 / 04 / 4200 / 1Repaired · 2026-07-02
E-7b9b33921ba865f5Step 3.7 FlashUnder-covered36.414752 / 4 / 06 / 6300 / 1Repaired · 2026-07-02
E-01a1df4eac0e6aefInklingUnder-covered44.714644 / 6 / 010 / 10500 / 1Repaired · 2026-07-24
E-ae60ed096a69eeffInklingUnder-covered56.014925 / 5 / 010 / 10500 / 1Repaired · 2026-07-24
E-824ec3caceabd338Grok 4.5Under-covered71.715127 / 7 / 014 / 14700 / 1First pass · 2026-07-24
E-9f28818a3063ee74Grok 4.5Under-covered40.214842 / 4 / 06 / 6300 / 1Repaired · 2026-07-18
E-c0bc4ff29a3cbf96Grok 4.5Under-covered60.315154 / 4 / 08 / 8400 / 1Repaired · 2026-07-18
E-4aac1b6621aeae38Grok Build 0.1Under-covered26.415312 / 0 / 02 / 2100 / 1Repaired · 2026-07-02
E-ad48cf51fe7da3ccMiMo-V2.5Under-covered27.515332 / 0 / 02 / 2100 / 1Repaired · 2026-07-02
E-faaa866ee28d6401MiMo-V2.5Under-covered34.214972 / 2 / 04 / 4200 / 1Repaired · 2026-07-02
E-9c228ad72a159b33MiMo-V2.5-ProUnder-covered25.315282 / 0 / 02 / 2100 / 1Repaired · 2026-07-02

GB2-05: Hex leaderboard

Entrants are ranked by relative per-game score (0–100). Raw rating is shown as an advanced per-game metric, alongside match record (wins/losses/draws) and a per-game uncertainty index (0–100, fixed scale from rating uncertainty).

Reasoning level: Balanced Game: GB2-05: Hex

Scroll sideways to see every column.

GB2-05: Hex - Balanced filter
Rank Model Score Contributing programs Raw Elo W / L / D Uncertainty
1Claude Opus 5100.011598.19/1/0100.0
2Claude Opus 596.811590.38/2/0100.0
3Gemini 3.6 Flash82.111585.56/0/0100.0
4GPT-5.4 Nano80.411581.46/0/0100.0
5GPT-5.575.011550.36/2/0100.0
6Gemini 3.6 Flash71.811530.16/4/0100.0
7Grok 4.571.711512.37/7/085.3
8Grok 4.560.311514.84/4/0100.0
9Kimi K2.7 Code59.411558.44/0/0100.0
10GPT 558.611528.64/2/0100.0
11GPT-5.6 Terra57.011506.94/4/0100.0
12Claude Fable 556.211504.94/4/0100.0
13Inkling56.011491.95/5/0100.0
14Gemini 3.5 Flash53.711499.04/4/0100.0
15GPT-5.6 Luna48.311531.53/1/0100.0
16Gemma 4 31B47.411529.23/1/0100.0
17Gemini 3.1 Flash Lite44.811495.33/3/0100.0
18Inkling44.711464.54/6/0100.0
19Grok 4.540.211484.22/4/0100.0
20Claude Opus 4.840.111466.23/5/0100.0
21GPT-5.436.511502.92/2/0100.0
22Step 3.7 Flash36.411475.02/4/0100.0
23Qwen3.7 Plus36.411502.72/2/0100.0
24MiMo-V2.534.211497.32/2/0100.0
25GPT-5.4 Mini34.111469.52/4/0100.0
26GPT-5.4 Mini34.011469.32/4/0100.0
27GPT-5.4 Mini33.411495.62/2/0100.0
28GPT-OSS 120B33.311467.52/4/0100.0
29Claude Sonnet 533.111494.72/2/0100.0
30Gemini 3.5 Flash Lite30.411442.62/6/0100.0
31MiMo-V2.527.511533.22/0/0100.0
32Grok Build 0.126.411530.72/0/0100.0
33Kimi K326.411530.52/0/0100.0
34Gemini 3.5 Flash Lite25.711418.62/8/0100.0
35MiMo-V2.5-Pro25.311527.92/0/0100.0
36O324.311473.51/3/0100.0
37Qwen3.7 Max23.211470.81/3/0100.0
38GPT-5.4 Nano21.211438.21/5/0100.0
39GPT-5.6 Sol13.211446.60/4/0100.0
40GPT-5.4 Nano11.111441.60/4/0100.0
41Nex N2 Pro2.211472.10/2/0100.0
42GPT-5.4 Nano1.411470.20/2/0100.0
43Claude Opus 4.51.111469.50/2/0100.0
44Minimax M31.111469.30/2/0100.0
45North Mini Code0.011466.80/2/0100.0